Triple
T195715
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Department of Dermatology, Duke University |
E3814
|
entity |
| Predicate | subfield |
P450
|
FINISHED |
| Object | clinical dermatology |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: clinical dermatology | Statement: [Department of Dermatology, Duke University, subfield, clinical dermatology]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: subfield Context triple: [Department of Dermatology, Duke University, subfield, clinical dermatology]
-
A.
subtitle
Indicates that one work serves as a secondary or explanatory title to another, typically appearing beneath the main title.
-
B.
subfamily
Indicates that one taxonomic group is a subfamily within a larger family, representing an intermediate rank in biological classification.
-
C.
subclassOf
Indicates that one class is a more specific type of another class, inheriting its characteristics as a subset of it.
-
D.
subjectMatter
chosen
Indicates the topic, theme, or content area that something (such as a work, document, or discussion) is about.
-
E.
section
Indicates that one entity is a distinct part, division, or segment of another entity within a larger whole.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69a2548debd48190ae3a06d6e65b53c6 |
completed | Feb. 28, 2026, 2:35 a.m. |
| NER | Named-entity recognition | batch_69a25983b49c819080f7e161904c53da |
completed | Feb. 28, 2026, 2:57 a.m. |
| PD | Predicate disambiguation | batch_69a25677da14819094cd02868fd30c83 |
completed | Feb. 28, 2026, 2:44 a.m. |
Created at: Feb. 28, 2026, 2:41 a.m.